X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html_beautifulsoup.py;h=f5e03b52e96808d7db6a21efd656d0541d3ed976;hb=9ee993e850d08b63d9cc10dd2da8340574e9a6a0;hp=8f82d249669df7a7d79cc0a203103596f4284936;hpb=5240de604c92063107e41cd00c6b363498d65fa6;p=bookmarks_db.git

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index 8f82d24..f5e03b5 100644
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -87,12 +87,16 @@ def parse_html(filename, charset=None, log=None):
       # Lookup TITLE in the root
       title = root.title
 
-   if title is None:
-      title = ''
-   elif title.string:
-      title = title.string.encode(_charset)
-   else:
-      title = str(title)
+   if title is not None:
+      if title.string:
+         title = title.string.encode(_charset)
+      else:
+         parts = []
+         for part in title:
+            if not isinstance(part, basestring):
+               part = unicode(part)
+            parts.append(part.strip())
+         title = ''.join(parts).encode(_charset)
 
    meta = head.find(_find_contenttype, recursive=False)
    if meta: